@inproceedings{asada-etal-2026-citation,
    title = "Citation-Aware Continual Pre-Training for Biomedical Language Models",
    author = "Asada, Masaki  and
      Tsujimura, Tomoki  and
      Ishigaki, Tatsuya  and
      Egami, Shusaku  and
      Fukuda, Ken  and
      Takamura, Hiroya",
    editor = "Demner-Fushman, Dina  and
      Ananiadou, Sophia  and
      Roberts, Kirk  and
      Tsujii, Junichi",
    booktitle = "{B}io{NLP} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.bionlp-1.32/",
    pages = "407--412",
    ISBN = "979-8-89176-434-7",
    abstract = "The biomedical literature contains rich structured knowledge, including citation links that encode relationships between scientific studies, but such information is typically ignored in standard language model pre-training. We propose a citation-aware continual pre-training method for decoder-only language models that incorporates citation graph information from PubMed into next-token prediction by placing citation-linked abstract pairs within a shared context. We evaluate our method on multiple biomedical QA benchmarks using two model families. Results show that citation-aware continual pre-training achieves higher average accuracy than both the original base models and citation-unaware pre-training across biomedical tasks."
}